AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles (e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities, and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.

Contextualized representations (e.g. ELMo, BERT) have become the default pretrained representations for downstream NLP applications. In some settings, this transition has rendered their static embedding predecessors (e.g. Word2Vec, GloVe) obsolete. As a side-effect, we observe that older interpretability methods for static embeddings -while more mature than those available for their dynamic counterparts -are underutilized in studying newer contextualized representations. Consequently, we introduce simple and fully general methods for converting from contextualized representations to static lookup-table embeddings which we apply to 5 popular pretrained models and 9 sets of pretrained weights. Our analysis of the resulting static embeddings notably reveals that pooling over many contexts significantly improves representational quality under intrinsic evaluation. Complementary to analyzing representational quality, we consider social biases encoded in pretrained representations with respect to gender, race/ethnicity, and religion and find that bias is encoded disparately across pretrained models and internal layers even for models that share the same training data. Concerningly, we find dramatic inconsistencies between social bias estimators for word embeddings.

No abstract

Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models. First, we taxonomize the vast space of potential scenarios (i.e. use cases) and metrics (i.e. desiderata) that are of interest for LMs. Then we select a broad subset based on coverage and feasibility, noting what's missing or underrepresented (e.g. question answering for neglected English dialects, metrics for trustworthiness). Second, we adopt a multi-metric approach: We measure 7 metrics (accuracy, calibration, robustness, fairness, bias, toxicity, and efficiency) for each of 16 core scenarios to the extent possible (87.5% of the time), ensuring that metrics beyond accuracy don't fall to the wayside, and that trade-offs across models and metrics are clearly exposed. We also perform 7 targeted evaluations, based on 26 targeted scenarios, to more deeply analyze specific aspects (e.g. knowledge, reasoning, memorization/copyright, disinformation). Third, we conduct a large-scale evaluation of 30 prominent language models (spanning open, limited-access, and closed models) on all 42 scenarios, including 21 scenarios that were not previously used in mainstream LM evaluation. Prior to HELM, models on average were evaluated on just 17.9% of the core HELM scenarios, with some prominent models not sharing a single scenario in common. We improve this to 96.0%: now all 30 models have been densely benchmarked on a set of core scenarios and metrics under standardized conditions. Our evaluation surfaces 25 top-level findings concerning the interplay between different scenarios, metrics, and models. For full transparency, we release all raw model prompts and completions publicly 3 for further analysis, as well as a general modular toolkit for easily adding new scenarios, models, metrics, and prompting strategies. 4 We intend for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models.

High quality data forms the bedrock for building meaningful statistical models in NLP. Consequently, data quality must be evaluated either during dataset construction or post hoc. Almost all popular summarization datasets are drawn from natural sources and do not come with inherent quality assurance guarantees. In spite of this, data quality has gone largely unquestioned for many recent summarization datasets. We perform the first large-scale evaluation of summarization datasets by introducing 5 intrinsic metrics and applying them to 10 popular datasets. We find that data usage in recent summarization research is sometimes inconsistent with the underlying properties of the datasets employed. Further, we discover that our metrics can serve the additional purpose of being inexpensive heuristics for detecting generically low quality examples.